Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2401 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.5565. Min Act: -0.0000

Data Index: 607976 (C4 (Web Text))

Max Activating Token Index: 971

Text #1

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.2297. Min Act: -0.0000

Data Index: 574662 (C4 (Web Text))

Max Activating Token Index: 545

Text #2

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.1486. Min Act: -0.0000

Data Index: 996769 (C4 (Web Text))

Max Activating Token Index: 159

Text #3

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.1766. Min Act: -0.0000

Data Index: 172850 (C4 (Web Text))

Max Activating Token Index: 74

Text #4

Max Range: 3.5565. Min Range: -3.5565

Max Act: 2.9335. Min Act: -0.0000

Data Index: 515956 (C4 (Web Text))

Max Activating Token Index: 116

Text #5

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.0885. Min Act: -0.0000

Data Index: 25088 (C4 (Web Text))

Max Activating Token Index: 877

Text #6

Max Range: 3.5565. Min Range: -3.5565

Max Act: 2.9300. Min Act: -0.0000

Data Index: 442791 (C4 (Web Text))

Max Activating Token Index: 546

Text #7

Max Range: 3.5565. Min Range: -3.5565

Max Act: 3.0705. Min Act: -0.0000

Data Index: 721563 (C4 (Web Text))

Max Activating Token Index: 406

Text #8

Max Range: 3.5565. Min Range: -3.5565

Max Act: 2.7693. Min Act: -0.0000

Data Index: 883636 (C4 (Web Text))

Max Activating Token Index: 710

Text #9

Max Range: 3.5565. Min Range: -3.5565

Max Act: 2.9041. Min Act: -0.0000

Data Index: 1142971 (C4 (Web Text))

Max Activating Token Index: 6

Text #10

Max Range: 3.5565. Min Range: -3.5565

Max Act: 2.8802. Min Act: -0.0000

Data Index: 522002 (C4 (Web Text))

Max Activating Token Index: 63

Text #11

Max Range: 3.5565. Min Range: -3.5565

Max Act: 2.5495. Min Act: -0.0000

Data Index: 58218 (C4 (Web Text))

Max Activating Token Index: 170

Text #12

Max Range: 3.5565. Min Range: -3.5565

Max Act: 2.8149. Min Act: -0.0000

Data Index: 495673 (C4 (Web Text))

Max Activating Token Index: 486

Text #13

Max Range: 3.5565. Min Range: -3.5565

Max Act: 2.6582. Min Act: -0.0000

Data Index: 446634 (C4 (Web Text))

Max Activating Token Index: 949

Text #14

Max Range: 3.5565. Min Range: -3.5565

Max Act: 2.7747. Min Act: -0.0000

Data Index: 228540 (C4 (Web Text))

Max Activating Token Index: 139

Text #15

Max Range: 3.5565. Min Range: -3.5565

Max Act: 2.6266. Min Act: -0.0000

Data Index: 1274929 (C4 (Web Text))

Max Activating Token Index: 524

Text #16

Max Range: 3.5565. Min Range: -3.5565

Max Act: 2.7783. Min Act: -0.0000

Data Index: 264608 (C4 (Web Text))

Max Activating Token Index: 222

Text #17

Max Range: 3.5565. Min Range: -3.5565

Max Act: 2.8951. Min Act: -0.0000

Data Index: 915824 (C4 (Web Text))

Max Activating Token Index: 661

Text #18

Max Range: 3.5565. Min Range: -3.5565

Max Act: 2.6964. Min Act: -0.0000

Data Index: 1092912 (C4 (Web Text))

Max Activating Token Index: 65

Text #19

Max Range: 3.5565. Min Range: -3.5565

Max Act: 2.5431. Min Act: -0.0000

Data Index: 106940 (C4 (Web Text))

Max Activating Token Index: 311